jaidevd

Things that the regular code of conduct missed out

1. Thou shalt not slam the door when thou leaveth the auditorium.
2. Thou shalt take care not to kick the seat in front of you in the auditorium.
3. Thou shalt make sure that thy phone is silenced.
4. Thou shalt not jump the queue for lunch or tea.
5. Thou shalt speak only in whispers if a session is in progress.

jaidevd

#! /usr/bin/env python
# -*- coding: utf-8 -*-
# vim:fenc=utf-8

"""
Training Word embeddings on the MTsamples dataset.
"""

from keras.models import Model
from keras.layers import Dense, Embedding, Input, Reshape, Dot

jaidevd

#! /usr/bin/env python
# -*- coding: utf-8 -*-
# vim:fenc=utf-8
from __future__ import print_function

for i in range(1, 10):
    print(i)
    if i % 2 == 0:
        exit

jaidevd

#! /usr/bin/env python
# -*- coding: utf-8 -*-
# vim:fenc=utf-8
#
# JSM product code
#
# (C) Copyright 2018 Juxt SmartMandate Pvt Ltd
# All right reserved.
#
# This file is confidential and NOT open source.  Do not distribute.

jaidevd

```
for each epochs:
  * divide the training data into minibatches
  for each minibatch:
    * backpropagate and update weights
```

jaidevd

Deep Learning with the Scientific Method

The Problem

As technology becomes cheaper and more available, we start taking it for granted. Nowhere is this more true than in machine learning. As machines become cheaper and data becomes more and more voluminous, our approach to specific machine learning problems often, and understandably, becomes haphazard. Since GPUs are much cheaper and more widely available than ever before, we implicitly believe that throwing enough artificial neurons at a problem will eventually solve it. While this by itself may be true, it is not uncommon for ML practitioners to realize - unfortunately only in hindsight - that most of the iterations required to build a successful predictive model were unnecessary. Ironically, these 'missteps' are often what lead us to the correct answer. Solving a machine learning problem is like traversing a minefield, where the safest path can only be determined by blowing up a significantly large number of mines. You can only figure out the right a

jaidevd

#!/usr/bin/env python
# coding: utf-8

# In[1]:


get_ipython().run_line_magic('load_ext', 'autoreload')
get_ipython().run_line_magic('autoreload', '2')

jaidevd

{
  "$schema": "https://vega.github.io/schema/vega/v4.json",
  "description": "https://gramener.invisionapp.com/d/main/#/console/7709561/326727774/preview",
  "width": 495,
  "height": 320,
  "autosize": "fit",
  "padding": {
    "left": 5,
    "top": 25,
    "right": 100,

jaidevd

jaidevd

{
  "$schema": "https://vega.github.io/schema/vega/v5.json",
  "description": "A heatmap showing average daily temperatures in Seattle for each hour of the day.",
  "width": 800,
  "height": 500,
  "padding": 5,

  "title": {
    "text": "Seattle Annual Temperatures",
    "anchor": "middle",